Abstract not found

This paper addresses the issues of detecting and localizing objects in a scene that are both seen and heard. We explain the benefits of a human-like configuration of sensors (binaural and binocular) for gathering auditory and visual observations. It is shown that the detection and localization problem can be recast as the task of clustering the audio-visual observations into coherent groups. We propose a probabilistic generative model that captures the relations between audio and visual observations. This model maps the data into a common audio-visual 3D representation via a pair of mixture models. Inference is performed by a version of the expectationmaximization algorithm, which is formally derived, and which provides cooperative estimates of both the auditory activity and the 3D position of each object. We describe several experiments with single- and multiple-speaker detection and localization, in the presence of other audio sources.

Abstract. We address the issue of identifying and localizing individuals in a scene that contains several people engaged in conversation. We use a human-like configuration of sensors (binaural and binocular) to gather both auditory and visual observations. We show that the identification and localization problem can be recast as the task of clustering the audio-visual observations into coherent groups. We propose a probabilistic generative model that captures the relations between audio and visual observations. This model maps the data to a representation of the common 3D scene-space, via a pair of Gaussian mixture models. Inference is performed by a version of the Expectation Maximization algorithm, which provides cooperative estimates of both the activity and the 3D position of each speaker. Key words: multiple speaker localization, audio-visual integration, unsupervised clustering 1

The problem of multimodal clustering arises whenever the data are gathered with several physically different sensors. Observations from different modalities are not necessarily aligned in the sense there there is no obvious way to associate or compare them in some common space. A solution may consist in considering multiple clustering tasks independently for each modality. The main difficulty with such an approach is to guarantee that the unimodal clusterings are mutually consistent. In this letter, we show that multimodal clustering can be addressed within a novel framework: conjugate mixture models. These models exploit the explicit transformations that are often available between an unobserved parameter space (objects) and each of the observation spaces (sensors). We formulate the problem as a likelihood maximization task and derive the associated conjugate expectation-maximization algorithm. The convergence properties of the proposed algorithm are thoroughly investigated. Several local and global optimization techniques are proposed in order to increase its convergence speed. Two initialization strategies are proposed and compared. A consistent model selection criterion is proposed. The algorithm and its variants are tested and evaluated within the task of 3D localization of several speakers using both auditory and visual data. 1